M Abreu1, L Yi-Ching, A L Abreu. 1. Department of Stomatology, Federal University of Santa Catarina School of Dentistry, Florianopolis, SC, Brasil. murillo@ccs.ufsc.br
Abstract
OBJECTIVE: To compare the diagnostic performances provided by tuned aperture computed tomography (TACT) slices and the multiple images that they originate from in the detection of primary caries on the proximal surfaces of posterior teeth. STUDY DESIGN: Eight direct digital radiography images of each of 40 posterior teeth were acquired with a digital sensor. These source images were used to generate TACT slices of the teeth. Eight trained observers were calibrated in the use of both TACT slices and the eight source images of each tooth. They were asked to assess the presence/absence of proximal caries in the teeth using a 5-point rating scale. Observers' assessments were compared with the ground truth provided by histological examination of tooth sections. Areas under the receiver operating characteristic (ROC) curves (Az) were calculated for each combination of observer and image modality. Analysis of variance (ANOVA) was used to test the ROC values for potential statistical differences. RESULTS: Mean ROC Az values were 0.760 for TACT slices and 0.771 for its multiple source images for the detection of primary proximal caries. ANOVA showed no statistically significant differences either between modalities (P = 0.656) or between observers (P = 0.851). CONCLUSION: TACT slices and its multiple source images provide comparable diagnostic performance for proximal caries detection.
OBJECTIVE: To compare the diagnostic performances provided by tuned aperture computed tomography (TACT) slices and the multiple images that they originate from in the detection of primary caries on the proximal surfaces of posterior teeth. STUDY DESIGN: Eight direct digital radiography images of each of 40 posterior teeth were acquired with a digital sensor. These source images were used to generate TACT slices of the teeth. Eight trained observers were calibrated in the use of both TACT slices and the eight source images of each tooth. They were asked to assess the presence/absence of proximal caries in the teeth using a 5-point rating scale. Observers' assessments were compared with the ground truth provided by histological examination of tooth sections. Areas under the receiver operating characteristic (ROC) curves (Az) were calculated for each combination of observer and image modality. Analysis of variance (ANOVA) was used to test the ROC values for potential statistical differences. RESULTS: Mean ROC Az values were 0.760 for TACT slices and 0.771 for its multiple source images for the detection of primary proximal caries. ANOVA showed no statistically significant differences either between modalities (P = 0.656) or between observers (P = 0.851). CONCLUSION: TACT slices and its multiple source images provide comparable diagnostic performance for proximal caries detection.